no code implementations • 24 Jul 2023 • Raavi Gupta, Sameep Chattopadhyay, Pradyumna Paruchuri, Debasish Chatterjee
This article presents a novel numerically tractable technique for synthesizing Lyapunov functions for equilibria of nonlinear vector fields.
no code implementations • 3 Jul 2023 • Pradyumna Paruchuri, Debasish Chatterjee
For a hypothesis space realized as a compact but not necessarily convex subset of a finite-dimensional subspace of some underlying Banach space, this algorithm computes the Chebyshev radius and the Chebyshev center of the hypothesis space, thereby solving the problem of optimal recovery of functions from data.
no code implementations • 6 Sep 2022 • Ashwin Aravind, Debasish Chatterjee, Ashish Cherukuri
Apprenticeship learning is a framework in which an agent learns a policy to perform a given task in an environment using example trajectories provided by an expert.
no code implementations • 25 May 2022 • Ashutosh Jindal, Debasish Chatterjee, Ravi Banavar
In this article, we present explicit estimates of the size of the domain on which the Implicit Function Theorem and the Inverse Function Theorem are valid.
no code implementations • 5 Jul 2020 • Mohammed Rayyan Sheriff, Debasish Chatterjee
In this article, we dwell into the class of so-called ill-posed Linear Inverse Problems (LIP) which simply refers to the task of recovering the entire signal from its relatively few random linear measurements.
no code implementations • 8 Jun 2020 • Prabhat K. Mishra, Sanket S. Diwale, Colin N. Jones, Debasish Chatterjee
A stochastic model predictive control framework over unreliable Bernoulli communication channels, in the presence of unbounded process noise and under bounded control inputs, is presented for tracking a reference signal.
Optimization and Control
no code implementations • 19 Oct 2019 • Mohammed Rayyan Sheriff, Debasish Chatterjee
A dictionary is a database of standard vectors, so that other vectors / signals are expressed as linear combinations of dictionary vectors, and the task of learning a dictionary for a given data is to find a good dictionary so that the representation of data points has desirable features.
no code implementations • 16 Aug 2019 • Mohammed Rayyan Sheriff, Debasish Chatterjee
In this article we dwell into the class of so called ill posed Linear Inverse Problems (LIP) in machine learning, which has become almost a classic in recent times.
no code implementations • 4 Jun 2019 • Mishal Assif P K, Debasish Chatterjee, Ravi Banavar
Moreover, we perform a detailed study of both the asymptotic behaviour (consistency) and finite time behaviour of the scenario approach in the more general setting of nonconvex minmax optimization problems.
no code implementations • 18 Oct 2017 • Mohammed Rayyan Sheriff, Debasish Chatterjee
Dictionaries are collections of vectors used for representations of elements in Euclidean spaces.
no code implementations • 7 Mar 2016 • Mohammed Rayyan Sheriff, Debasish Chatterjee
Dictionaries are collections of vectors used for representations of random vectors in Euclidean spaces.